基于平面重建与自然特征匹配的虚实注册方法

针对增强现实系统中的三维注册问题,提出了一种新的基于多平面结构三维重建与自然特征匹配相结合的虚实注册方法,该方法分为离线三维重建和在线实时注册两个阶段.离线阶段系统利用两幅参考图像和双目视觉原理恢复出平面坐标系,并根据用户指定的世界坐标系计算两者之间的变换关系.实时注册阶段,系统首先将当前图像与参考图像做特征匹配以获取平面所对应的单应性关系,进而恢复出每个平面所对应的投影矩阵,由上述投影矩阵以及离线计算所获得的世界坐标系与多个平面坐标系之间的变换关系合成三维注册所需的变换矩阵.实验结果表明,该方法是有效可行的,而且在克服误差积累方面较传统方法有明显改善.

Registration based on plane reconstruction and natural features tracking

In this paper, a novel registration method based on multi-planes reconstruction and natural feature tracking is presented. Our method can be divided into two stages: offline 3D reconstruction and online registration. In offline stage, the planes and world coordinate systems are established based on natural feature matches and projective reconstruction technique. In online stage, natural features detected from the reference images are tracked in the current frame by the Best Bin First (BBF) method. With the obtained correspondences, the homography between the world planes and the current frame is robustly calculated by using PROSAC and nonlinear least square method. Then, the registration matrix is synthesized based on the above homography and the transform matrices between the planes and world coordinate system obtained in offline stage. Some experiments demonstrate the validity of the proposed approach that can improve the performance to solve error accumulation.